Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Doc: Oss 339 unexpected intent policy #11982

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

vitordiniz25
Copy link
Contributor

Proposed changes:

  • I added the UnexpecTEDIntentPolicy on the handling unexpected input section in the documentation.
    Status (please check what you already did):
  • added some tests for the functionality
  • updated the documentation
  • updated the changelog (please check changelog for instructions)
  • reformat files using black (please check Readme for instructions)

@CLAassistant
Copy link

CLAassistant commented Jan 31, 2023

CLA assistant check
All committers have signed the CLA.

@vitordiniz25 vitordiniz25 changed the title Oss 339 unexpected intent policy Doc: Oss 339 unexpected intent policy Feb 1, 2023
Copy link
Contributor

@radovanZRasa radovanZRasa left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hello @vitordiniz25 thank you for your contribution.
Unfortunately we cannot review it until you sign a contributor license.

@vitordiniz25
Copy link
Contributor Author

I've just signed! :)

Comment on lines +105 to +113
`UNexpecTEDIntentPolicy` helps you review conversations and also allows your bot to react to unlikely user inputs.
It is an auxiliary policy that should only be used with at least one other policy, as the only that it can trigger is the special
`action_unlikely_intent` action.

`UNexpecTEDIntentPolicy` has the same model architecture as `TEDPolicy`.

The difference is at a task level. Instead of predicting the next probable action, this policy
predicts whether the last predicted intent is a likely intent according to the training stories
and conversation context.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This content is actually the same as on this page, could you please add a short sentence of how this is relevant for handling unexpected input and then link to the corresponding section in docs/docs/policies.mdx#unexpected-intent-policy.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please also add a changelog entry of type doc.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants